Deep learning models have demonstrated great success in various computer vision tasks such as image classification and object tracking. However, tracking the lumbar spine by digitalized video fluoroscopic imaging (DVFI), which can quantitatively analyze the motion mode of spine to diagnose lumbar instability, has not yet been well developed due to the lack of steady and robust tracking method. In this paper, we propose a novel visual tracking algorithm of the lumbar vertebra motion based on a Siamese convolutional neural network (CNN) model. We train a full-convolutional neural network offline to learn generic image features. The network is trained to learn a similarity function that compares the labeled target in the first frame with the candidate patches in the current frame. The similarity function returns a high score if the two images depict the same object. Once learned, the similarity function is used to track a previously unseen object without any adapting online. In the current frame, our tracker is performed by evaluating the candidate rotated patches sampled around the previous frame target position and presents a rotated bounding box to locate the predicted target precisely. Results indicate that the proposed tracking method can detect the lumbar vertebra steadily and robustly. Especially for images with low contrast and cluttered background, the presented tracker can still achieve good tracking performance. Further, the proposed algorithm operates at high speed for real time tracking.
Super-resolution is being considered as one of the important goals for optical imaging and image processing. In this paper, we present a novel imaging technique that exceeds the limit of resolving power of diffraction-limited optical system to achieve super-resolution imaging, by combining the advantages of compressive sensing and complex annular filters. This technique is realized by utilizing a classical 4F optical system with a phase-only spatial light modulator. Furthermore, the feasibility of this technique is theoretically analyzed, and physically validated by laboratory experiments. Experimental results demonstrated that this technique improves the resolving power of diffraction-limited optical system by approximately 1.58 times, and the intensity image of high-resolution object can be recovered from 25% of the total number of measurements.
This paper proposes a novel imaging technique which combines clustering sub-dictionary learning and gradient histogram preservation to improve the quality of compressive imaging from two aspects: edge sharpness and noise suppression. Practical experiments further demonstrate better results on practical optical imaging application in terms of weighted peak signal-to-noise ratio and measure of feature similarity index.